techexplorist.com

AI can predict peak warming of the Earth

Stanford University researchers have found that the global objective of limiting warming to 1.5 degrees Celsius above pre-industrial levels is now nearly unattainable. Their findings indicate that the hottest years on record are likely yet to come, potentially breaking existing temperature records.

There is a 50% chance that global warming could exceed 2 degrees Celsius, even if humanity meets current goals of rapidly reducing greenhouse gas emissions to net-zero by the 2050s.

Previous studies, including key assessments by the Intergovernmental Panel on Climate Change, have suggested that decarbonization at this rate would typically help keep global warming below 2 degrees, but the urgency for accelerated action has never been clearer.

“We’ve been seeing accelerating impacts around the world in recent years, from heatwaves and heavy rainfall and other extremes. This study suggests that, even in the best-case scenario, we are very likely to experience conditions that are more severe than what we’ve been dealing with recently,” said Stanford Doerr School of Sustainability climate scientist Noah Diffenbaugh, who co-authored the study with Colorado State University climate scientist Elizabeth Barnes.

This year is set to beat 2023 as Earth’s hottest year on record, with global average temperatures expected to exceed 1.5 degrees Celsius or nearly 2.7 degrees Fahrenheit above the pre-industrial baseline before people started burning fossil fuels widely to power industry.

A new study reveals a staggering nine-in-ten probability that the hottest year of this century will be at least half a degree Celsius warmer, even if rapid decarbonization efforts are implemented. Leveraging AI to improve climate projections, researchers Diffenbaugh and Barnes have developed a sophisticated system that predicts how high global temperatures could soar based on varying decarbonization strategies.

In training their AI, the researchers tapped into extensive archives of climate model simulations, analyzing temperature and greenhouse gas data. By feeding the AI actual historical temperatures alongside a range of widely accepted scenarios for future greenhouse gas emissions, they have laid the groundwork for more accurate predictions of future warming.

“AI is emerging as an incredibly powerful tool for reducing uncertainty in future projections. It learns from the many climate model simulations that already exist, but its predictions are then further refined by real-world observations,” said Barnes, who is a professor of atmospheric science at Colorado State.

The research contributes to an expanding collection of studies suggesting that the opportunity to meet the more ambitious target of the 2015 Paris Climate Agreement has likely passed, where nearly 200 countries committed to keeping long-term temperature rises “well below” 2 degrees while striving to limit increases to 1.5 degrees.

A second recent study by Barnes and Diffenbaugh indicates that various regions, such as South Asia, the Mediterranean, Central Europe, and certain parts of sub-Saharan Africa, could experience more than 3 degrees Celsius of warming by 2060 if emissions continue to rise—earlier than previous studies had predicted.

The significance of extremes Both recent studies expand upon 2023 research by Diffenbaugh and Barnes, which estimated the remaining years until the 1.5 and 2 degrees Celsius targets are exceeded. However, since these benchmarks are calculated based on average conditions over extended periods, they do not fully capture the severity of possible climate extremes.

“As we watched these severe impacts year after year, we became more and more interested in predicting how extreme the climate could get even if the world is fully successful at rapidly reducing emissions,” said Diffenbaugh, the Kara J Foundation Professor and Kimmelman Family Senior Fellow at Stanford.

In a scenario where emissions achieve net-zero by the 2050s – the most optimistic prediction commonly used in climate models – the researchers discovered a 90% likelihood that the warmest year of this century will be at least 1.8 degrees Celsius above the pre-industrial average, with a two-thirds chance for at least 2.1 degrees Celsius.

In a situation where emissions decrease too gradually to reach net zero by 2100, Diffenbaugh and Barnes observed a 90% probability that the hottest year would be 3 degrees Celsius above the pre-industrial average. In this context, many areas could face temperature anomalies that are at least three times greater than those recorded in 2023.

The new predictions underline the importance of investing not only in decarbonization but also in measures to make human and natural systems more resilient to severe heat, intensified drought, heavy precipitation, and other consequences of continued warming.

Traditionally, these adaptation initiatives have been prioritized less than decarbonization efforts, with funds allocated for reducing carbon emissions surpassing those for adaptation in global climate finance and legislation like the 2022 Inflation Reduction Act.

“Our results suggest that even if all the effort and investment in decarbonization is as successful as possible, there is a real risk that, without commensurate investments in adaptation, people and ecosystems will be exposed to climate conditions that are much more extreme than what they are currently prepared for,” Diffenbaugh said.

Journal reference:

Noah S. Diffenbaugh, Elizabeth A. Barnes. Data-Driven Predictions of Peak Warming Under Rapid Decarbonization. Geophysical Research Letters, 2024; DOI: 10.1029/2024GL111832

Read full news in source page